Tag: inference-efficiency

Sep 09, 2026

• large-language-models
• adaptive-compute
• layer-routing
• recurrent-depth
• dynamic-compute
• test-time-compute
• inference-efficiency

Aug 31, 2026

• entity
• masked-diffusion
• sparse-decoding
• inference-efficiency

Aug 31, 2026

• diffusion-language-models
• vision-language-models
• masked-diffusion
• multimodal-understanding
• inference-efficiency

Aug 31, 2026

• diffusion-language-models
• unified-multimodal-models
• masked-diffusion
• kv-cache
• sparse-decoding
• inference-efficiency

Aug 31, 2026

• diffusion-language-models
• language-modeling
• generation
• inference-efficiency

Jul 17, 2026

• entity
• diffusion-language-models
• parallel-decoding
• inference-efficiency
• self-distillation

Jul 17, 2026

• diffusion-language-models
• parallel-decoding
• self-distillation
• inference-efficiency
• post-training

Jul 17, 2026

• linear-attention
• recurrent-state
• state-space-models
• long-context
• inference-efficiency
• hybrid-models

Jul 17, 2026

• linear-attention
• recurrent-state
• exact-memory
• kv-cache
• associative-recall
• long-context
• inference-efficiency

Jul 17, 2026

• hybrid-models
• associative-memory
• recurrent-state
• kv-cache
• long-context
• inference-efficiency

Jul 17, 2026

• diffusion-language-models
• masked-diffusion
• bidirectional-attention
• inference-efficiency
• llm-post-training

Jun 30, 2026

• linear-attention
• recurrent-state
• state-space-models
• long-context
• inference-efficiency

Jun 30, 2026

• hybrid-models
• long-context
• recurrent-state
• attention
• inference-efficiency
• fixed-flops

May 18, 2026

• sequence-models
• state-space-models
• recurrent-models
• inference-efficiency
• language-modeling